YKY, I see that great minds think alike.
We had a discussion here a couple of years back, to the effect that if you differentiate signals leading into a NN, and integrate the results from a NN, that you then get the same as if you didn't do the integration and differentiation. However, "learning" in such a system would then become temporal learning. Of course, differentiation, which is widely utilized in living systems, is only possible in CONTINUOUS systems. Temporal learning appears to be necessary to develop intelligence, differentiation appears to be necessary to develop temporal learning, and continuous operation appears to be necessary to support differentiation. I have seen several computational approaches to nearly continuous operation: 1. Utilize very fine time quanta, e.g. >>1kHz, and start testing in dynamic environments. This would be least disruptive to present efforts, but is also the least efficient method. 2. Instead of communicating simple values, also communicate dv/dt and perhaps higher order terms to support quasi-continuous operation. 3. Extending on the above approach, communicate formulas that represent the present situation in ways where time is just another parameter. This would also support bidirectional computing, that I believe is also a necessary requirement. 4. Move to a programmable analog platform. There ARE ways past the usual objections to this approach, but no one seems to be interested in investing the ~$100M to launch in this direction. Done right, this could also support bidirectional computing. Your observation that continuous operation is probably necessary is good, but still not entirely sufficient to get AGI working. Besides continuous and bidirectional operation, I wonder what ELSE is needed to close this gap?!!! Our present stepwise unidirectional concept of computing is MUCH too puny to support AGI. Surveying this landscape is a conversation that we really need to have, before true AGI can even get started. Steve ========= On Tue, Jan 27, 2015 at 5:12 AM, YKY (Yan King Yin, 甄景贤) via AGI < [email protected]> wrote: > *The idea:* make programs continuous and then evolve programs using > continuous techniques. Valiant's recent book "Probably Approximately > Correct" has said something about evolving continuous parameters for strong > AI. (It may be more tractable than evolving programs with discrete > elements, the kind of programs we have known usually). > > *In the context of logic-based AI* (such as OpenCog, NARS, and my > Genifer) the idea is to make all logic and procedural statements > continuous. The part concerning making logic continuous is via > algebraization which I have been looking into, but will discuss elsewhere. > The "procedural" aspect can be realized by letting the AGI control a Turing > machine (TM) with one or more tapes, and by making such a Turing machine > "continuous". > > As a first step towards continuous TMs, we can start with *finite state > machines (FSM)*. It seems that a continuous version of FSMs corresponds > to continuous dynamical systems (aka topological dynamical systems). I > have not looked into the details of this correspondence, but it looks > fairly straightforward. > > *To make TMs continuous* is somewhat more difficult. One way is to turn > the "tape read/write operations" into states of an FSM (in such case the > number of states may become infinite). But I'm not sure if that is a good > way to create continuous TMs. > > Any other idea for continuous TMs? > > Thanks in advance =) > -- > *YKY* > *"The ultimate goal of mathematics is to eliminate any need for > intelligent thought"* -- Alfred North Whitehead > *AGI* | Archives <https://www.listbox.com/member/archive/303/=now> > <https://www.listbox.com/member/archive/rss/303/10443978-6f4c28ac> | > Modify > <https://www.listbox.com/member/?&;> > Your Subscription <http://www.listbox.com> > -- Full employment can be had with the stoke of a pen. Simply institute a six hour workday. That will easily create enough new jobs to bring back full employment. ------------------------------------------- AGI Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657 Powered by Listbox: http://www.listbox.com
